From:	 Linus Torvalds <torvalds@transmeta.com>
To:	 Ben LaHaise <bcrl@redhat.com>
Subject: Re: [RFC][DATA] re "ongoing vm suckage"
Date:	 Fri, 3 Aug 2001 20:48:03 -0700 (PDT)
Cc:	 Daniel Phillips <phillips@bonn-fries.net>,
	 Rik van Riel <riel@conectiva.com.br>,
	 <linux-kernel@vger.kernel.org>, <linux-mm@kvack.org>


You might try this approach instead, which just removes the thing that
might deadlock and always is unfair..

(Ugh, I hate attachements, but the system I'm sending this from has this
broken version of 'pine' that will mess up white-space).

For nicer interactive behaviour while flushing things out, the
inode_fsync() thing should really use "write_locked_buffers()". That's a
separate patch, though.

		Linus

diff -u --recursive --new-file pre3/linux/drivers/block/ll_rw_blk.c linux/drivers/block/ll_rw_blk.c
--- pre3/linux/drivers/block/ll_rw_blk.c	Thu Jul 19 20:51:23 2001
+++ linux/drivers/block/ll_rw_blk.c	Fri Aug  3 20:28:43 2001
@@ -119,17 +119,10 @@
 int * max_sectors[MAX_BLKDEV];
 
 /*
- * queued sectors for all devices, used to make sure we don't fill all
- * of memory with locked buffers
+ * How many reqeusts do we allocate per queue,
+ * and how many do we "batch" on freeing them?
  */
-atomic_t queued_sectors;
-
-/*
- * high and low watermark for above
- */
-static int high_queued_sectors, low_queued_sectors;
-static int batch_requests, queue_nr_requests;
-static DECLARE_WAIT_QUEUE_HEAD(blk_buffers_wait);
+static int queue_nr_requests, batch_requests;
 
 static inline int get_max_sectors(kdev_t dev)
 {
@@ -592,13 +585,6 @@
 	 */
 	if (q) {
 		/*
-		 * we've released enough buffers to start I/O again
-		 */
-		if (waitqueue_active(&blk_buffers_wait)
-		    && atomic_read(&queued_sectors) < low_queued_sectors)
-			wake_up(&blk_buffers_wait);
-
-		/*
 		 * Add to pending free list and batch wakeups
 		 */
 		list_add(&req->table, &q->pending_freelist[rw]);
@@ -1032,16 +1018,6 @@
 	for (i = 0; i < nr; i++) {
 		struct buffer_head *bh = bhs[i];
 
-		/*
-		 * don't lock any more buffers if we are above the high
-		 * water mark. instead start I/O on the queued stuff.
-		 */
-		if (atomic_read(&queued_sectors) >= high_queued_sectors) {
-			run_task_queue(&tq_disk);
-			wait_event(blk_buffers_wait,
-			 atomic_read(&queued_sectors) < low_queued_sectors);
-		}
-
 		/* Only one thread can actually submit the I/O. */
 		if (test_and_set_bit(BH_Lock, &bh->b_state))
 			continue;
@@ -1168,26 +1144,9 @@
 	memset(max_readahead, 0, sizeof(max_readahead));
 	memset(max_sectors, 0, sizeof(max_sectors));
 
-	atomic_set(&queued_sectors, 0);
 	total_ram = nr_free_pages() << (PAGE_SHIFT - 10);
 
 	/*
-	 * Try to keep 128MB max hysteris. If not possible,
-	 * use half of RAM
-	 */
-	high_queued_sectors = (total_ram * 2) / 3;
-	low_queued_sectors = high_queued_sectors / 3;
-	if (high_queued_sectors - low_queued_sectors > MB(128))
-		low_queued_sectors = high_queued_sectors - MB(128);
-
-
-	/*
-	 * make it sectors (512b)
-	 */
-	high_queued_sectors <<= 1;
-	low_queued_sectors <<= 1;
-
-	/*
 	 * Scale free request slots per queue too
 	 */
 	total_ram = (total_ram + MB(32) - 1) & ~(MB(32) - 1);
@@ -1200,10 +1159,7 @@
 	if ((batch_requests = queue_nr_requests >> 3) > 32)
 		batch_requests = 32;
 
-	printk("block: queued sectors max/low %dkB/%dkB, %d slots per queue\n",
-						high_queued_sectors / 2,
-						low_queued_sectors / 2,
-						queue_nr_requests);
+	printk("block: %d slots per queue, batch=%d\n", queue_nr_requests, batch_requests);
 
 #ifdef CONFIG_AMIGA_Z2RAM
 	z2_init();
@@ -1324,4 +1280,3 @@
 EXPORT_SYMBOL(generic_make_request);
 EXPORT_SYMBOL(blkdev_release_request);
 EXPORT_SYMBOL(generic_unplug_device);
-EXPORT_SYMBOL(queued_sectors);
diff -u --recursive --new-file pre3/linux/include/linux/blkdev.h linux/include/linux/blkdev.h
--- pre3/linux/include/linux/blkdev.h	Mon Jul 30 10:45:59 2001
+++ linux/include/linux/blkdev.h	Fri Aug  3 20:30:01 2001
@@ -174,8 +174,6 @@
 
 extern int * max_segments[MAX_BLKDEV];
 
-extern atomic_t queued_sectors;
-
 #define MAX_SEGMENTS 128
 #define MAX_SECTORS 255
 
@@ -203,14 +201,7 @@
 		return 512;
 }
 
-#define blk_finished_io(nsects)				\
-	atomic_sub(nsects, &queued_sectors);		\
-	if (atomic_read(&queued_sectors) < 0) {		\
-		printk("block: queued_sectors < 0\n");	\
-		atomic_set(&queued_sectors, 0);		\
-	}
-
-#define blk_started_io(nsects)				\
-	atomic_add(nsects, &queued_sectors);
+#define blk_finished_io(nsects)	do { } while (0)
+#define blk_started_io(nsects)	do { } while (0)
 
 #endif